AI Biz Hub for Agents

Put the inputs in the query string. Agents that can only fetch pages get the computed result, the inputs that used defaults, the method page and a citation line:

https://aibizhub.io/api/run/freelance-rate-capacity-planner?target_annual_income=120000&billable_utilization_percent=65

{
  "calculator": "freelance-rate-capacity-planner",
  "input": {
    "target_annual_income": 120000,
    "billable_utilization_percent": 65
  },
  "defaults_used": {
    "annual_business_overhead": 22000,
    "tax_rate_percent": 28,
    "buffer_percent": 15,
    "working_weeks_per_year": 46,
    "working_hours_per_week": 40,
    "project_hours": 35
  },
  "result": {
    "minimumViableHourlyRate": 157.75,
    "targetHourlyRate": 181.41,
    "…": "…"
  },
  "provenance": {
    "methodology": "https://aibizhub.io/freelance-rate-capacity-planner/",
    "engine_sha256": "…",
    "…": "…"
  },
  "cite": "AI Biz Hub, Freelance Rate & Capacity Planner (engine …), https://aibizhub.io/api/run/freelance-rate-capacity-planner?…"
}

• Add format=md (or send Accept: text/markdown) for a markdown answer.
• POST the inputs as a JSON object to the same URL for nested inputs.
• An unknown or out-of-range input is a 400 that names the field and shows a working example.
• Every calculator with its inputs, units, defaults and an example run: /api/tools (search with ?q=runway).

Add https://aibizhub.io/mcp as a remote MCP server (Streamable HTTP) in any client that accepts a server URL. No sign-in; stateless; both the 2026-07-28 protocol and the earlier initialize-based revisions work.

Three tools: find_calculator (the calculators that answer a question, with input schemas), run_calculator and list_calculators. One tool per calculator would cost an agent tens of thousands of tokens of context; these cost a few hundred.

Every tool ships its pure compute as a static ES module at /engines/{slug}.js. Import the module and call compute(input). The same formulas as the calculator pages. Input is validated against the published contract: an unknown field, a wrong type or a value outside its allowed range throws an Error that names the field. Each module ships typed .d.ts declarations; self-contained ES2020+ for browsers, Deno and Bun (in Node, download the file first, or use the URL API above).

const { compute } = await import('https://aibizhub.io/engines/freelance-rate-capacity-planner.js');
const result = compute({
  target_annual_income: 120000,
  billable_utilization_percent: 65
});
// { minimumViableHourlyRate, targetHourlyRate, stretchHourlyRate, ... }

• No authentication required
• Each engine is self-contained — no external imports, no runtime dependencies
• Deterministic results, cacheable forever at the edge
• Input params use snake_case matching contract fields
• Input/output JSON Schemas at /engines/manifest.json

Tools are organized into 5 decision clusters. Use these to route users to the right area:

When benchmark data is available for a tool's output, the engine compute() result includes a benchmarks field:

"benchmarks": {
  "hourly_rate": {
    "p25": 55,
    "median": 85,
    "p75": 130,
    "source": "U.S. Bureau of Labor Statistics (OEWS)",
    "sourceUrl": "https://www.bls.gov/oes/current/oes_nat.htm",
    "year": 2024,
    "context": "US, freelance-adjusted"
  }
}

Sources: BLS (public domain), OpenView SaaS Benchmarks, Paddle Subscription Index, Mailchimp, Content Marketing Institute. All data is from public or openly published research.

People should start at the decision guide, the homepage, or browse all calculators.

Agents should start from agent-tools.json, match the user's intent to a tool, and run it with /api/run/{slug} or the MCP server, or import /engines/{slug}.js when running code. A calculator page fetched without JavaScript shows its default inputs, not the user's.